© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8122
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TICK
    -0.28
     approvals
    -0.27
    èľ±
    -0.27
    ael
    -0.26
    drs
    -0.25
    Ticks
    -0.25
    [#
    -0.25
    :?
    -0.24
    å¡«æĬ¥
    -0.24
    [table
    -0.24
    POSITIVE LOGITS
    imes
    0.27
    çļĦä¸ĢäºĽ
    0.26
    #region
    0.26
    ÂŃi
    0.26
    ile
    0.26
    amic
    0.24
    æĻ¶
    0.24
    éĥ¨éŨ
    0.24
    家纺
    0.24
    Putting
    0.24
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.